Chapter 4Fault-tolerant Data-fusion Method:Application on Platoon Vehicle Localization 1
4.1. Introduction
For several years, active security methods as well as intelligent technical devices have mostly been developed in public or private transport vehicles. Sophisticated methods from robotics, such as localization, obstacle detection and trajectory planning, are now available in intelligent transport systems. The implementation of these new functions strongly depends on the quality of data coming from different sensors embedded in vehicles as well as their merging, particularly when it comes to critical information that must be supplied for autonomous navigation systems.
The goal of our research within the framework of the FD2S project carried out by GIS 3SGS was to integrate the concept of tolerance to faults, failures or inaccuracy of sensors. The goal was to integrate the detection, diagnostics and processing of faults in the sensor data for data fusion, which requires the validation/invalidation of data collected, and the decision-making concerning the reconfiguration of the data fusion algorithm. These functionalities play an essential role in providing autonomy in order to give a vehicle (or a robot) the capability to adapt and react to unforeseen events, thus allowing it to fulfill the goals of its mission. This is a decisive element in improving the operational efficiency of intelligent transport systems and decreasing the cognitive load of their piloting.
Our research ...
Get Supervision and Safety of Complex Systems now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
